Skip to main content

awkno — The man page for the Aither World

Docs · Source · pip install awkno · The Aither World

The Aither World is an operating system for agents — a Linux you can hand to one, the runtimes it works in, and the tools it works with. awnix is the Linux underneath it; awkno is one of its 33 bricks — each installs on its own, runs offline, and needs no account.

Start here: Ask it what a brick does and get the answer with your network cable out.

Every brick, stack, and law in your terminal, offline.

awkno is a standalone reference for the Aither World ecosystem — the set of portable, composable tools and principles that make agent automation reproducible and auditable. No browser, no internet connection, no external dependencies needed.

Why

Agent systems need documented principles. The Aither World is built on 18 laws derived from real failures on production systems — lessons about gates, silence, atomicity, and delivery that apply to every agent work you build.

The ecosystem itself is ~36 portable tools (bricks) organized into thematic stacks. awkno brings them all into your terminal: any brick's purpose and adoption path, any law's principle and reasoning, any stack's composition and status — all offline, all fast, queryable by keyword, and open to reading and redistribution.

Quick Start

Install

pip install awkno

Use

# Show a brick
awkno awdk
awkno awsh

# Show a law
awkno law 5

# List everything
awkno list

# Search for a term
awkno search agent
awkno -k silence

# Raw output for piping
awkno awdk --plain
awkno --json awdk

No Arguments

awkno

Shows the overview: command summary, quick start examples, and how to explore further.

What's Inside

Bricks (36 tools)

Portable, single-purpose tools that do one job well and compose with others:

  • awdk — Build AI agent fleets (3 lines, any backend)
  • awskills — Portable agent skills (self-contained procedures)
  • awm — Scoped agent memory (tenant:user:project boundaries)
  • awgit — Semantic version control (edit-ops, leases)
  • awgraph — Code graph for agents (AST, call graphs)
  • awrelay — Agent messaging (findings, alerts, coordination)
  • awmail — Email for agents (send and receive)
  • And 29 more...

Each has an "adopt" sentence: the smallest useful thing you can do with it alone, without adopting anything else.

Stacks (9 collections)

Curated sets of bricks that work together:

  • agent-vm — The bare agent VM
  • agent-senses — Perception (search, pages)
  • shared-worktree — Many agents, one repo
  • the-front-door — Identity, authority, record
  • And 5 more...

Laws (18 principles)

Lessons learned in production, written down so they don't have to be re-derived:

  1. A rule nothing asserts is a suggestion
  2. Make it a check, not a ticket
  3. Watch your gate fail
  4. Mutate the test, not just the code
  5. Design for the silence
  6. A check that cannot run must not pass
  7. The symptom names the innocent
  8. A checker in the wrong place found nothing
  9. Detection without delivery is not detection
  10. A gate that floods gets switched off
  11. Open green; ratchet down
  12. Measure it again
  13. Written is not deployed
  14. You wrote it; that does not mean it ships
  15. Generate, never copy
  16. The defect lives in the union
  17. Fail closed, then prove the happy path
  18. Never trust the caller

Architecture

Offline-First Design

The corpus is generated once from ecosystem.yaml and awskills/codex/laws/, then committed as JSON data files under awkno/pages/. After install, the package needs no external files or network.

This means:

  • No runtime generation (fast startup)
  • No external dependencies beyond stdlib
  • Reproducible across machines and time
  • Auditable: every page is in the repo

CLI Features

  • Pager support: Automatic pagination on TTY (via $PAGER or system default)
  • TTY-aware formatting: ANSI bold headers only when connected to a terminal
  • Multiple output modes:
    • --plain — No ANSI codes (safe for piping to other tools)
    • --json — Structured output for scripting
    • Default — Man-page-style formatted text
  • Fuzzy search: Type something close, get ranked results
  • Command shortcuts:
    • awkno list — Show all topics grouped by category
    • awkno law N — Show law by number
    • awkno -k TERM / awkno --apropos TERM — Search (like man -k)

No Internal Leakage

This package is built for public distribution, and the corpus is GENERATED from an internal registry -- so the generator strips, and the build then re-checks, every category of internal detail: infrastructure hostnames, absolute paths from the build machine, issue-tracker and quality-gate identifiers, and imports that only resolve inside a private monorepo.

The point of scanning the generated corpus rather than the generator is that a sanitiser is only as good as its last pattern. A page that slips through reads as ordinary prose, so nothing downstream would ever notice.

Development

Regenerate the Corpus

python awkno/generate.py

The generator reads:

  • ecosystem.yaml — The brick and stack registry
  • awskills/codex/laws/*.md — The 18 laws

And writes JSON to awkno/pages/.

Test Locally

pip install -e .
pytest

# Or run the CLI directly
python -m awkno.cli awdk

Build and Publish

pip install build
python -m build

# Publish to PyPI
twine upload dist/*

Integration

In Your Own Code

from awkno import AwknoRegistry

registry = AwknoRegistry()
page = registry.get("awdk")
print(page.render())

# Search
results = registry.search("agent memory")
for page, score in results[:5]:
    print(f"{page.topic}: {page.synopsis}")

# List by category
bricks = registry.list_by_category("brick")
laws = registry.list_by_category("law")

As a Dependency

awkno has zero runtime dependencies (PyYAML is dev-only, for corpus generation).

[project]
dependencies = [
    "awkno",
]

Contributing

Read a law, apply it, send a pull request. The package itself is small and well-documented.

Pages are generated from ecosystem.yaml and law files — edits to those files flow into awkno on the next generation.

License

Apache 2.0. See LICENSE.

Further Reading


awkno — read the principles once, apply them everywhere.

The aw family

Standalone tools that share one idea: replace something you would otherwise have to trust with something you can check.

Each installs on its own, works offline, and needs no account.

instead of trusting you check
awdk a framework's idea of how your agents should run one loop you can read, pointed at a backend you already pay for
awskills that an agent knows your procedure the procedure written down, versioned, and loadable by any agent
awm that memory stayed in its lane tenant:user:project scopes, so a write cannot cross a boundary
awnode a vendor's cloud with every prompt a local gateway routing to backends you chose
awgraph that grep found everything an AST + tree-sitter call graph an agent can traverse
awgit that no one else is editing this file a lease, refused at commit time if you do not hold it
awseal that the artifact came from who you think an Ed25519 seal — the key that verifies is not the key that forges
awshare that the download is intact content-addressed bundles, verified on fetch
awnest that there is a person on the other end a verdict with evidence, where "we could not tell" is not "yes"
awnboard a share link anyone who sees it can use an invitation addressed to one person, for one gate, revocable
awnix that the box is what you left it as an immutable image you built, with atomic rollback
awrecover that the restore worked a restore that fully lands or does not land at all
awkno (you are here) that the docs site is up, or that you remember the family the whole ecosystem in your terminal, with no network at all
awrelay a SaaS in the middle of your agents findings, alerts and coordination over your own transport
awmail a mailbox somebody else can read mail your agents send and receive over your own server
awfind one vendor's idea of the web results from whichever providers you configured
awbrowse that the page said what you were told the render, the DOM and the requests it made
aitherkvcache a vendor's quantisation defaults sub-byte KV cache kernels you can benchmark yourself
AitherZero a pile of scripts nobody has numbered numbered, discoverable automation with declarative playbooks
AitherConnect what a page tells your browser to do a federated search and desktop bridge you host
awreason a confident paragraph the phases it went through, and every tool call it made to get there
awrecurse that everything you pasted in was actually read which slices it opened, and what it concluded from each
awprism the first explanation that fits the ranked alternatives, and the observation that separates them
awrepl what the agent believes the value is the value, printed from the live session
awresearch a summary of pages nobody opened every claim against the source it came from
awpredict a model because it trained without erroring its prediction against a self-updating lookup, on the rows that are actually novel
awkno (you are here) that the docs site is up, or that you remember the family the whole ecosystem in your terminal, with no network at all

awnix is the ground floor — A Linux you can hand to an agent — immutable base, capabilities included.

The Aitherium ecosystem

Every repository here is public. Each publishes an aither-manifest.json beside its page, so any surface can read every sibling's — the network is browsable from any node in it.

repo what it is pages
awdk Build AI agent fleets — 3 lines, any backend, local or cloud docs
awskills Portable agent skills — self-contained procedures an agent loads on demand docs
awm A portable, scoped agent memory docs
awnode A lightweight local gateway — bridges your apps to the AI backends you chose docs
awrun A priority-aware queue and dispatcher for agentic runs and ad-hoc CI builds docs
awgraph A semantic code graph for agents — AST + tree-sitter, call graphs docs
awgit Semantic version control on top of git — edit-ops and leases docs
awseal Sign an artifact so a stranger can verify it docs
awshare Publish an artifact and fetch it back verified docs
awdit An append-only audit trail whose gaps are DETECTABLE docs
awbac Role-based access control that fails closed and explains itself docs
awiam Who is this caller? A directory and session store that fails honestly docs
awtunnel Reach a service that has no public address docs
awnest Prove there is a human before you let them into the nest docs
awnboard A front gate you can put in front of anything, and hand someone the key to docs
awnix A Linux you can hand to an agent — immutable base, capabilities included docs
awrecover Labelled snapshots with an all-or-nothing restore docs
awkno (you are here) The man page for the Aither World — every brick, stack and law, offline docs
awrelay Portable agent messaging — findings, alerts, coordination docs
awmail Give an agent an email address — send, and actually receive docs
awnet The agentic web — agents host a mesh, and agents join one docs
awfind A portable search client — query, results, ranking docs
awbrowse A portable browser client — navigate, console, network, DOM, screenshot docs
awknowledge How to run a coding agent so the result survives — the laws, with evidence docs
aitherkvcache Near-optimal KV cache quantization for LLM inference — sub-byte compression docs
AitherZero PowerShell 7+ automation framework — numbered, self-describing scripts docs
AitherConnect Browser extension — federated AI search, page context, and the Living OS overlay docs
awreason A portable reasoning client — sessions, phases, thoughts, and the chain that produced the answer docs
awrecurse Answer a question over a context far larger than the window — recursively, with the trace kept docs
awprism Turn a failure into ranked hypotheses — and say what would confirm each one docs
awrepl A REPL an agent can actually use — state that survives between turns docs
awresearch Ask a research question, get a cited report you can check docs
awpredict Predict what your environment does next, and how surprised you were docs
awkno (you are here) The man page for the Aither World — every brick, stack and law, offline docs
<script src="aither-constellation.js"></script>

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

awkno-0.1.0.tar.gz (95.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

awkno-0.1.0-py3-none-any.whl (124.0 kB view details)

Uploaded Python 3

File details

Details for the file awkno-0.1.0.tar.gz.

File metadata

  • Download URL: awkno-0.1.0.tar.gz
  • Upload date:
  • Size: 95.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.3

File hashes

Hashes for awkno-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a1004fcf0ccc42610e571bd592e1bfd28ab1d0d333684b52f57f58d889257ba7
MD5 eb1740ef8d5c00912d5df8a10c22a811
BLAKE2b-256 e2307e158d4585c020a6dd853a192d74d77eb2fa4a574d5b25d68152eb35c6aa

See more details on using hashes here.

File details

Details for the file awkno-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: awkno-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 124.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.3

File hashes

Hashes for awkno-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 bfb91e455b25245d6730d009ff8c77ad595222fabebcd7e672165d303d89b073
MD5 32b250905d9e0657eabb867fe1a971b9
BLAKE2b-256 f91773a53b07e7d21e69d1d707514b6583216480bfdbd67477eda21336fe0f5f

See more details on using hashes here.

Release history Release notifications | RSS feed

0.2.2

2 files

0.2.1

2 files

0.2.0

2 files

This release

0.1.0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page